© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40208
    Prev
    Next
    INDEX
    Explanations

    placenta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elman
    -0.25
    |--
    -0.25
     |--
    -0.25
     jud
    -0.25
     especial
    -0.24
    STRUCTIONS
    -0.24
     Unblock
    -0.24
     nowhere
    -0.24
    reon
    -0.24
    笼
    -0.23
    POSITIVE LOGITS
    åĪģ
    0.28
    miss
    0.26
    oi
    0.26
    Bomb
    0.26
    Sync
    0.26
     quo
    0.25
    /Peak
    0.25
    thon
    0.25
    umont
    0.25
    Oi
    0.24
    Activations Density 0.295%

    No Known Activations